Comparison of Disease Patterns and Outcomes Between Non-Japanese and Japanese Patients at a Single Tertiary Emergency Care Center in Japan.

BACKGROUND: Japan's historically low immigration rate and monolingual culture makes it a particularly interesting setting for clarifying non-national medical care. Our study objective was to examine disease patterns and outcome differences between Japanese and non-Japanese patients in a rapidly globalizing nation. METHODS: A secondary data analysis of 325 non-Japanese and 13,370 Japanese patients requiring tertiary care or intensive-care unit or high-care unit admission to the emergency department at the Tokyo Medical and Dental University medical hospital from 2010 through 2019 was conducted. Multivariable linear and logistic regressions models were applied to examine differences in percentage of diagnosis, mortality rates, and length of stay, stratified by Glasgow Coma Scale (GCS) scores to consider the impact of language barriers. Sex and age were adjusted. RESULTS: Non-Japanese patients had more anaphylaxis, burns, and infectious disease, but less cardiovascular diagnoses prior to adjustment. After adjustment, there were significantly more anaphylaxis (adjusted odds ratio [aOR] 2.7; 95% confidence interval [CI], 1.7-4.4) and infectious disease diagnoses (aOR 2.2; 95% CI, 1.3-3.7), and marginally more burn diagnoses (aOR 2.3; 95% CI, 0.96-5.3) than Japanese patients. Regardless of GCS scores, there were no significant differences between non-Japanese and Japanese patient length of stay for anaphylaxis, burn, and infectious disease after covariate adjustment. CONCLUSION: There were more non-Japanese patients diagnosed with anaphylaxis, burns, and infectious disease, but no notable patient care differences for length of stay. Further prevention efforts are needed against anaphylaxis, burns, and infectious disease for non-Japanese tourists or residents.

Development, validation, and feature extraction of a deep learning model predicting in-hospital mortality using Japan's largest national ICU database: a validation framework for transparent clinical Artificial Intelligence (cAI) development.

OBJECTIVE: While clinical Artificial Intelligence (cAI) mortality prediction models and relevant studies have increased, limitations including the lack of external validation studies and inadequate model calibration leading to decreased overall accuracy have been observed. To combat this, we developed and evaluated a novel deep neural network (DNN) and a validation framework to promote transparent cAI development. METHODS: Data from Japan's largest ICU database was used to develop the DNN model, predicting in-hospital mortality including ICU and post-ICU mortality by days since ICU discharge. The most important variables to the model were extracted with SHapley Additive exPlanations (SHAP) to examine the DNN's efficacy as well as develop models that were also externally validated. MAIN RESULTS: The area under the receiver operating characteristic curve (AUC) for predicting ICU mortality was 0.94 [0.93-0.95], and 0.91 [0.90-0.92] for in-hospital mortality, ranging between 0.91-0.95 throughout one year since ICU discharge. An external validation using only the top 20 variables resulted with higher AUCs than traditional severity scores. CONCLUSIONS: Our DNN model consistently generated AUCs between 0.91-0.95 regardless of days since ICU discharge. The 20 most important variables to our DNN, also generated higher AUCs than traditional severity scores regardless of days since ICU discharge. To our knowledge, this is the first study that predicts ICU and in-hospital mortality using cAI by post-ICU discharge days up to over a year. This finding could contribute to increased transparency on cAI applications.

The advent of medical artificial intelligence: lessons from the Japanese approach.

Artificial intelligence or AI has been heralded as the most transformative technology in healthcare, including critical care medicine. Globally, healthcare specialists and health ministries are being pressured to create and implement a roadmap to incorporate applications of AI into care delivery. To date, the majority of Japan's approach to AI has been anchored in industry, and the challenges that have occurred therein offer important lessons for nations developing new AI strategies. Notably, the demand for an AI-literate workforce has outpaced training programs and knowledge. This is particularly observable within medicine, where clinicians may be unfamiliar with the technology. National policy and private sector involvement have shown promise in developing both workforce and AI applications in healthcare. In combination with Japan's unique national healthcare system and aggregable healthcare and socioeconomic data, Japan has a rich opportunity to lead in the field of medical AI.